Automatic Data Classification and Tagging with ML Data Catalog

To really make a Data Catalog usable, data needs to be classified based on the semantic definition of data, enriched with data profiles, and linked to the business definition and attributes to make it usable.

The current solution for this is manual curation, tagging, and annotating data. This is impractical and unsustainable as the data landscape and volume continue to grow.

DvSum uses machine learning to automatically classify, and curate the data by combining physical data definitions, profiles, and taxonomies. It further tags the data automatically. For example, it can tag datasets as Reference, Master, or Transactional. It can tag data elements on data privacy classification and sensitivity levels.

Watch the 2 minute tutorial to see it in action.